@agent360/browser-mcp
io.github.Agent360dk/browser-mcp · version 1.31.0 · 2,425 weekly npm downloads · audited 2026-11-03
Notes
Findings
No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.
Claude Connectors Directory readiness
- ❌ Every tool has a title Missing on 40 of 40: browser_navigate, browser_get_page_content, browser_extract_list, browser_screenshot and 36 more
- ❌ Every tool declares readOnlyHint or destructiveHint Missing on 40 of 40: browser_navigate, browser_get_page_content, browser_extract_list, browser_screenshot and 36 more
- ✅ Tool names are 64 characters or fewer All within limit
- ❌ Descriptions avoid instructions about model behavior or other tools 15 of 40 descriptions reference other tools or tell the model what it must do: browser_navigate, browser_extract_list, browser_screenshot, browser_click_xy and 11 more
- ✅ No hidden instructions or invisible characters in tool metadata None found
Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.
What this server's tools can do
- Runs shell commands or code:
browser_execute_script - Makes outbound web requests:
browser_navigate,browser_fetch - Has delete or destructive operations:
browser_drop_file
Not a vulnerability by itself. It tells you what an injected prompt could ask this server to do, so you can decide which tools need approval.
Supply chain
- Install scripts: none
- npm provenance: yes
- Source repository linked: yes
- License: MIT
- Direct dependencies: 2
Tools (40)
| Name | Title | Hint | Description |
|---|---|---|---|
browser_navigate | none | Navigate the active browser tab to a URL. Reuses the current tab by default (no tab spam). Pass new_tab=true only when you need to keep the current page open. In the current tab the answer is ok:true only when Chrome too… | |
browser_get_page_content | none | Get the content of the current page as text or HTML. Pass `selector` to read one part of a large page instead of all of it - on a big logged-in app the full HTML can run past a million characters. The answer is capped at… | |
browser_extract_list | none | Read the rows of a long or virtualised list by scrolling its container until no new rows appear. Use this instead of browser_get_page_content whenever a page shows a repeating list longer than the viewport - mail lists (… | |
browser_screenshot | none | Take a screenshot of the visible area of the current tab. Returns base64 PNG, or saves to disk if path is provided. The image is in device pixels; when Chrome reports them in time, the answer also gives the CSS viewport … | |
browser_execute_script | none | Execute JavaScript in the current page, through the Chrome debugger (Runtime.evaluate) in the page's own context: the page's globals are visible and its Content Security Policy does not block it. A returned promise is aw… | |
browser_double_click | none | True double-click on an element (two trusted press/release pairs with escalating clickCount). Use for open-item actions (calendar events, file lists) where two single clicks would trigger inline-rename instead (e.g. OWA … | |
browser_right_click | none | Right-click an element (trusted CDP mouse events) to open page-level context menus (web apps like OWA/Google Docs render their own). Note: Chrome's NATIVE context menu does not open via CDP - only in-page menus. If the m… | |
browser_click_xy | none | ESCAPE HATCH: Click at raw viewport coordinates (CSS pixels) with fully trusted mouse events. Use when a visible button resists every selector strategy (Azure portal dialogs, Knockout-bound divs, canvas UIs): take a scre… | |
browser_reattach_debugger | none | RECOVERY: Force-detach and re-attach the Chrome debugger on the current tab. Use when interactive tools (click/fill/press_key) start timing out or reporting ghost-attach ("Debugger attach failed ... ghost") while list_ta… | |
browser_click | none | Click an element on the page. Supports CSS selectors AND text-based selectors. Auto-scrolls element into view. Uses real mouse events (works on Angular/React SPAs and CSP-strict sites like Google, Stripe). A text selecto… | |
browser_fill | none | Fill a form input field with a value. Supports CSS selectors AND text-based selectors. Auto-scrolls and focuses the element. Works on CSP-strict sites via Chrome Debugger API. For date inputs use browser_set_date, for au… | |
browser_press_key | none | Press a keyboard key (Enter, Tab, Escape, ArrowDown, etc.). Useful for submitting forms, navigating dropdowns, closing dialogs. Supports modifier keys (ctrl, alt, shift, meta). While ctrl, meta or alt is held, no charact… | |
browser_scroll | none | Scroll the page to an element or by pixel amount. Useful for reaching elements below the fold. | |
browser_wait | none | Wait for an element to appear on the page. Supports CSS and text-based selectors. | |
browser_hover | none | Hover over an element to trigger tooltips, dropdown menus, or hover states. Supports CSS and text selectors. If the mouse would not reach the target at its center - another element lies in front of it (an overlay, a dial… | |
browser_select_option | none | Select an option from a dropdown menu. Works with native <select> elements AND custom dropdowns (Angular Material, React Select, etc.). For custom dropdowns: clicks the trigger, waits for options, then clicks the matchin… | |
browser_dismiss_overlays | none | Dismiss visible popups, modals, tooltips, banners, and "Are you sure?"-style overlays in one call. Heuristic-based: finds close affordance via aria-label, text content (Skip/Cancel/Ikke nu/Don't show/Got it/Close), or × … | |
browser_set_combobox | none | Set value(s) on an autocomplete/combobox input. Handles the click → type query → wait for filtered listbox → click option flow as one MCP call. Supports multi-select (e.g., Languages on Meta Ads). Use when browser_select… | |
browser_drop_file | none | Handing a file to the page needs "Allow access to file URLs" for the Agent360 Browser MCP extension (off by default for Chrome Web Store installs); that switch also lets the extension open any local file as a page, so wh… | |
browser_set_date | none | Robustly set a date input - handles native <input type="date">, masked text inputs (e.g. MM/DD/YYYY), and calendar pickers (MUI, react-datepicker, AntD, Lexical/Meta). Tries native value-set, format-aware typing via Inpu… | |
browser_handle_dialog | none | Answer a JavaScript alert/confirm/prompt or "Leave site?" on the active tab. If a dialog this extension saw open is on screen and nobody is answering it, it is answered now, and the reply says what Chrome reports happene… | |
browser_wait_for_network | none | Wait for a network request to complete. Useful after clicking buttons that trigger API calls - ensures data is loaded before reading the page. Monitors real network traffic via Chrome DevTools Protocol. | |
browser_fetch | none | Make an HTTPS request from the extension background. It is not subject to the page's CORS or CSP, so it works for API calls (Google, Stripe, Slack) where a fetch from the page would be blocked. Your browser cookies are n… | |
browser_list_tabs | none | List the tabs this session owns (tabs it opened or adopted): id, URL, title, and each tab's active flag (whether Chrome shows it in front of its window, not which tab this session is working in). Tabs of other sessions a… | |
browser_get_cookies | none | Get cookies for a site this session has open in one of its tabs (the site itself, a parent domain or a subdomain). Navigate to the site first - cookies for sites the session is not working on are refused. | |
browser_get_local_storage | none | Read localStorage from the current page. Pass key for a specific value, or omit for all. | |
browser_set_cookies | none | Set one or more cookies for a domain. | |
browser_set_local_storage | none | Set a localStorage key-value pair on the current page. | |
browser_console_logs | none | Get recent console.log/warn/error messages from the page. Installs a lightweight interceptor on first call. Returns the last N console messages. | |
browser_ask_user | none | Ask the user to do something or give information. Without fields it shows a small card in the bottom-left corner that the user can drag away while they act on the page (log in, solve a CAPTCHA, give consent); with fields… | |
browser_list_frames | none | List all frames (iframes) in the current page with their URLs and indices. | |
browser_select_frame | none | Execute JavaScript in a specific frame by frame index, through the Chrome debugger in that frame's own context - also a frame from another site. Use browser_list_frames first to find the right index. A returned promise i… | |
browser_get_new_tab | none | Get the most recently opened tab (useful after clicking links that open new tabs, OAuth popups, etc.). | |
browser_switch_tab | none | Switch to a specific browser tab by ID. Get tab IDs from browser_list_tabs or browser_get_new_tab. The other tools then act on that tab. Chrome is not brought in front of the user: the tab is made active in its window, a… | |
browser_close_tab | none | Close a browser tab by ID. Only tabs owned by the current session can be closed. | |
browser_upload_file | none | Handing a file to the page needs "Allow access to file URLs" for the Agent360 Browser MCP extension (off by default for Chrome Web Store installs); that switch also lets the extension open any local file as a page, so wh… | |
browser_extract_token | none | Open a known provider's API page (stripe, hubspot, slack, shopify, mailchimp, pipedrive, calendly, google, linkedin) and get instructions for finding or creating its API credentials there. It reads nothing itself: read t… | |
browser_solve_captcha | none | Detect CAPTCHAs on the current page and work through them, one action per call. "detect" reports reCAPTCHA v2/v3, hCaptcha, Cloudflare Turnstile and FunCaptcha. "click_checkbox" tries the reCAPTCHA checkbox and detects a… | |
browser_about | none | Returns Browser MCP info and pre-filled URLs the user can click to submit feature wishes, share use-cases, or report bugs. Call this PROACTIVELY whenever the user (a) mentions a feature they wish existed ("I wish browser… | |
browser_provide_feedback | none | Self-diagnosis + feedback in one call. Call this AUTOMATICALLY, without asking the user, the moment Browser MCP itself gets in your way: a tool errors or times out, a tool does something other than what it promised, the … |
Check your own setup
npx mcpvetter scan --liveBadge
Add this to a README:
[](https://mcpvetter.com/servers/agent360-browser-mcp)Publish this server?
Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.